EUVIMEDOpdag EUVIMED
Crossref

Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse

Wenzhuo Ma, Zhenzhong Chen

ACM Transactions on Multimedia Computing, Communications, and Applications · 2025-12-31 · 21 (12) · 1-22

DOI: 10.1145/3761815 ↗

At a glance

Journal article in ACM Transactions on Multimedia Computing, Communications, and Applications, published online on 2025-11-21. Written by Wenzhuo Ma and 1 co-authors. Cited 18 times so far (Crossref); 59 references.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Recently, foundational diffusion models have attracted considerable attention in image compression tasks, whereas their application to video compression remains largely unexplored. In this article, we introduce DiffVC, a diffusion-based perceptual neural video compression framework that effectively integrates foundational diffusion model with the video conditional coding paradigm. This framework uses temporal context from previously decoded frame and the reconstructed latent representation of the current frame to guide the diffusion model in generating high-quality results. To accelerate the iterative inference process of diffusion model, we propose the Temporal Diffusion Information Reuse (TDIR) strategy, which significantly enhances inference efficiency with minimal performance loss by reusing the diffusion information from previous frames. Additionally, to address the challenges posed by distortion differences across various bitrates, we propose the Quantization Parameter-based Prompting (QPP) mechanism, which utilizes quantization parameters as prompts fed into the foundational diffusion model to explicitly modulate intermediate features, thereby enabling a robust variable bitrate diffusion-based neural compression framework. Experimental results demonstrate that our proposed solution delivers excellent performance in both perception metrics and visual quality.

Cite

APA

Ma, W., & Chen, Z. (2025). Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(12), 1-22. https://doi.org/10.1145/3761815

Vancouver

Ma W, Chen Z. Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(12):1-22. doi:10.1145/3761815

BibTeX
@article{Ma2025,
  author = {Ma, Wenzhuo and Chen, Zhenzhong},
  title = {Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2025},
  volume = {21},
  number = {12},
  pages = {1--22},
  doi = {10.1145/3761815}
}
Start for free →